During the recent times, technology has evolved to support agriculture. Technology provides a great assist to the traditional farming methods, increasing efficiency and output. It has become a resourceful aid for the farmers. Agriculture has been the backbone of the Indian economy producing a GDP of 18.3 in 2022–23. Due to the continuously growing population, farmers are striving to provide for the growing requirements, aiming at producing good yielding, high-quality products. The farmers face many challenges such as depletion of soil nutrients due to continuous growing of a particular crop, not being able to grow crop in its suitable soil environment. This paper works toward aiding these challenges with a study that employs soil analysis and supervised machine learning techniques and aims to improve crop prediction accuracy. This paper examines nine classification algorithms: Logistic Regression, Decision Tree, Gaussian Naïve Bayes, Support Vector Machine, K-Nearest Neighbors, Extra Tree, Random Forest, Bagging Classifier, and Gradient Boosting. The study found the Gaussian Naïve Bayes algorithm to be a standout performer with 99.55% accuracy.